7 papers
Geometric Entropy: When Trajectory Diversity Helps and Hurts in Imitation Learning
Qian Luo, Ruizhe Liu, Pei Zhou +2
We study how trajectory-shape diversity in demonstrations affects imitation learning (IL) performance across models, tasks, and data scales. We introduce Geometric Entropy (H_G), a…
DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation
Hanxiang Ren, Pei Zhou, Xunzhe Zhou +1
Language-conditioned manipulation policies typically process instructions and observations through shared network parameters. This task-state entanglement provides a pathway for ob…
Reinforcing Human Behavior Simulation via Verbal Feedback
Weiwei Sun, Xuhui Zhou, Jiarui Liu +13
Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying "that was rude" or a friend explaining "here's why that hurt"). Yet, learning from feedback for…
DexHoldem: Playing Texas Hold'em with Dexterous Embodied System
Feng Chen, Tianzhe Chu, Li Sun +6
Evaluating embodied systems on real dexterous hardware requires more than isolated primitive skills: an agent must perceive a changing tabletop scene, choose a context-appropriate…
Hyper-GoalNet: Goal-Conditioned Manipulation Policy Learning with HyperNetworks
Pei Zhou, Wanting Yao, Qian Luo +2
Goal-conditioned policy learning for robotic manipulation presents significant challenges in maintaining performance across diverse objectives and environments. We introduce Hyper-…
HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data
Ruizhe Liu, Pei Zhou, Qian Luo +4
Effective generalization in robotic manipulation requires representations that capture invariant patterns of interaction across environments and tasks. We present a self-supervised…